CN103528617A - Cockpit instrument automatic recognizing and detecting method and device - Google Patents
Cockpit instrument automatic recognizing and detecting method and device Download PDFInfo
- Publication number
- CN103528617A CN103528617A CN201310455647.9A CN201310455647A CN103528617A CN 103528617 A CN103528617 A CN 103528617A CN 201310455647 A CN201310455647 A CN 201310455647A CN 103528617 A CN103528617 A CN 103528617A
- Authority
- CN
- China
- Prior art keywords
- image
- instrument
- pixel
- value
- cockpit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000012545 processing Methods 0.000 claims abstract description 28
- 230000000007 visual effect Effects 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 7
- 210000002569 neuron Anatomy 0.000 claims description 36
- 238000001514 detection method Methods 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 24
- 230000001054 cortical effect Effects 0.000 claims description 23
- 238000006243 chemical reaction Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 239000000284 extract Substances 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000012217 deletion Methods 0.000 claims description 8
- 230000037430 deletion Effects 0.000 claims description 8
- 238000010304 firing Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 5
- 238000011946 reduction process Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000006386 memory function Effects 0.000 claims description 4
- 230000009467 reduction Effects 0.000 abstract description 5
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000003860 storage Methods 0.000 abstract description 4
- 238000007670 refining Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 8
- 238000007689 inspection Methods 0.000 description 8
- 238000012913 prioritisation Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 230000018109 developmental process Effects 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 241000124008 Mammalia Species 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005183 dynamical system Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 210000003746 feather Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000003534 oscillatory effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 210000000225 synapse Anatomy 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 210000000857 visual cortex Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a cockpit instrument automatic recognizing and detecting method, which comprises the following steps that instrument images are read; the images are sampled; nonlinear vector median filters are adopted for carrying out noise reduction processing on the images; overall and local threshold value methods are combined, instrument images are subjected to binaryzation, and binaryzation images are obtained; the images are refined, pointers are accurately detected, and the pointers subjected to refining processing become single pixel width pointers. The cockpit instrument automatic recognizing and detecting method has the advantages that an improved crossed visual model is utilized, and instrument edges are extracted; according to priori knowledge, the study training is carried out, similar features are found, and instruments are subjected to classified comparison; a gradient method is utilized, and the angle of the pointers is calculated; through the angle, the numerical value is calculated by combing the priori knowledge, and in addition, the storage display is carried out. Cockpit instruments are completely and automatically recognized and detected, the manual intervention is not needed, manpower resources can be greatly reduced, errors caused by subjective factors are avoided, and the cockpit instrument automatic recognizing and detecting method with good performance is provided.
Description
Technical field
The invention belongs to instrument detection technique field, relate in particular to the automatic identification of a kind of cockpit instrument and detection method and device.
Background technology
In human sciences's exploration and production practices activity, instrument and meter is important tool and the means in the understanding world, the difference that its Main Basis is measured, adopt certain transformational relation, by measuring mechanism, measured, be converted to that numeral shows or the size of angular displacement, realize reading, instrument has simple in structure, easy to use, the characteristic such as cheap, civilian, in military numerous areas such as grade, application is extremely extensive, especially for airborne equipment, from device context, debug, use, metering and alarm, to voltage, electric current, power, power factor, the isoparametric monitoring of frequency, all will take instrument as benchmark, therefore, the whether accurate reliability service to airborne equipment of instrument plays vital effect, people adopt the method for range estimation to come interpretation and calibrating pointer instrument traditionally, this method of discrimination is subject to people's subjective factor as people's observation angle, the impact such as observed range and fatigue strength, there is the unfavorable factors such as labour intensity is large, cannot realize that automaticdata reads and the automatic demand of regular inspection, first, the resolution characteristic of human eye is limited, when pointer is between two reticules, can only guestimate pointer position, the accurate indicating value of reading instrument, secondly, the whole course of work is loaded down with trivial details, repetitive operation is a lot, operator's sense of responsibility and visual fatigue have also had a strong impact on the order of accuarcy of verification, what is more important, the amount of having of cockpit instrument is larger, a large amount of instrument action need couplings are used, operating personnel just must accomplish very clear, therefore, this just reads with verification mode and has proposed stern challenge traditional instrument.
At present, general instrument check method can be classified as three classes substantially, one class can be described as " to show inspection table " method, one class is called " with source inspection table " method, up-to-date application is called " machine vision method ", " to show inspection table " method mainly be take manual operation as main, by third party, carry out the accuracy of observation watch, " with source inspection table " method is after having introduced microcomputor program control, the output of employing standard source, manually read by after the instrument registration of school, thereby calculate the error of each reticule, " machine vision method " is mainly appliance computer supplementary means, instrument is identified, interpretation, thereby the reading of calculating instrument list index.
Though convenient, quick advantage that the former detecting instrument has, detects the main manpower that relies on, it is larger that its accuracy, degree of accuracy are affected by subjective factor; Though the latter regulates standard volume and becomes more convenient, accurate, it also relies on artificial interpretation, corrects a mistake, so can not be widely used, therefore, designs and develops a kind of method that has the automatic identification of well behaved instrument and detect and seems particularly important.
With table inspection table " method is mainly according to standard GB/T/T7676.1-1998, according to the rules instrument is carried out to verification, the feature of the method is to utilize instrument that class of accuracy is higher as third party's truing tool, as " standard " in checking procedure, the class of accuracy of the simulation direct acting voltage table of indication and reometer is divided into: 0.05, 0.1, 0.2, 0.3, 0.5, 1, 1.5, 2, 2.5, 3 and 5 totally ten one grades, for example, under working method in accordance with regulations, the maximum cause error of the instrument of 0.2 grade is between ± 0.1%～± 0.2%, in like manner, the maximum cause error of the instrument of 0.5 grade is between ± 0.2%～± 0.5%, check meter is exactly the process of determining the affiliated scope of instrument maximum cause error, for 0.05 grade, the instrument of 0.1 grade and 0.2 grade is generally used as standard scale, the instrument of 0.5～2.5 grade is generally that laboratory is used, 2.5 grades of following instrument, generally that field monitor is used.
Generally by manual adjustments, control electric weight and export, watch the pointer position of tested instrument simultaneously attentively, observe and record data, then the error of calculation, draw verification conclusion.
With source inspection table " be actually a kind of " semi-automatic instrument check " method, it is more convenient that it regulates standard volume, more accurate, by adopting explicitly known standard source, carry out the dynamic range of observing apparatus, the error of measuring instrument can coincidence loss standard requirement, by adjusting the exact value of standard source, carry out the accurate error amount of measuring instrument, in addition, development along with photoelectric technology, on " with source inspection table " basis, someone attempts placing photoelectric sensitive device on pointer dashboard, according to pointer by the variation that is subject to the intensity of reflected light of this some when cautious of calibrated meter dish, utilize photoelectric effect to produce trigger pip, thereby obtain pointer in certain flashy position, as Japanese San Feng company's dial gauge somascope and the BJY-1 of Chengdu Univ. of Science & Technology dial gauge Automatic Check-out And Readiness Equipment, based on coincide point digital photogrammetry principle, with optical system by dial plate video imaging on shadow screen, in shadow screen fixed position, have light slit, so that photovalve receives sweep signal, thereby measure for the coincidence signal with each checkpoint space, by subsequent conditioning circuit, measured the error of each checkpoint.
" machine vision method " is important technology and the means of current pointer instrument quality testing, its recognition technology is mainly to utilize digital image processing techniques, complete image acquisition in this testing process, image conversion and storage, pointer location and detect, the key operation such as deviation detection, utilize that automatic control technology realizes pointer interpretation, analog quantity applies rejects with substandard product, simultaneously, utilize the superior data processing function of computing machine, complete demonstration, storage, inquiry and the report printing of testing result, realize the robotization of testing process
Existing technical matters has: 1, measuring process can not be full-automatic; 2, the amount consuming time of measuring is large; 3, measuring accuracy is low; 4, development cost is high.
Summary of the invention
The object of the embodiment of the present invention is to provide the automatic identification of a kind of cockpit instrument and detection method and device, be intended to solve measuring process that existing technology exists can not be automatically, the problem that amount consuming time is large, measuring accuracy is low, development cost is high of measurement.
The embodiment of the present invention is achieved in that a kind of cockpit instrument identification and detection method automatically, and described cockpit instrument automatically identifies and detection method comprises the following steps:
Read in Instrument image;
Image is sampled;
Adopt non-linear Vector median filtering to carry out noise reduction process to image;
Adopt overall situation and partial situation's threshold method to combine, by Instrument image binaryzation, obtain binary image;
Image is carried out to refinement, accurately detect pointer, the pointer after thinning processing becomes single pixel wide pointer;
Utilize improved intersection vision mode, extract instrument edge;
According to priori, carry out learning training, find similar features, to the instrument comparison of classifying;
Utilize gradient method, calculate the angle of pointer;
By angle, and in conjunction with priori, evaluation, and store demonstration.
Further, image binaryzation adopts improved 0STU method to carry out binary conversion treatment to image.
Further, 0STU method is carried out binary conversion treatment idiographic flow to image and is:
The first step, reading images, and according to the concrete size of image ranks, by Image Automatic Segmentation, be the subimage of a series of variable r * r, conveniently image is carried out to the division of block;
Second step, in neighborhood, according to meter performance, is divided into target and background, adds up the intensity profile of each pixel, and what tonal range was comparatively approached is classified as a class, and calculates mathematical expectation and the variance of 2 category feature points, according to classical OTSU criterion, finds out local threshold T
1 (i);
The 3rd step, carries out binary conversion treatment to window, after carry out the operation of circulation process second step, until searching image is complete;
The 4th step, for avoiding that the point of edges of regions is produced to erroneous judgement, is considered as a pixel by each region, and gray-scale value is threshold value T
1 (i), view picture is solved to expectation, covariance, find out global threshold, erroneous judgement point is repaired.
Further, thinning processing adopts 3x3 template to extract the skeleton of cockpit instrument.
Further, 3x3 template is extracted the skeleton concrete grammar of cockpit instrument and is:
Step 1, finds a pixel (i, j), makes pixel in image and the pixel matching in template A;
Step 6, repeating step (1) is to (5), otherwise, stop;
Further, extracting edge adopts intersecting visual cortical model to cut apart extraction to cockpit instrument.
Further, in intersecting visual cortical model each neuron for Last status F
ij[n-1] has memory function and state F
ijalong with its memory content of the variation of time can decay, the rate of decay is subject to the impact of decay factor f (f>1), and the mathematical expression of intersecting visual cortical model is as follows:
F
ij[n+1]=fF
ij[n]+S
ij+W
ij{Y}
T
ij[n+1]=gT
ij[n]+hY
ij[n+1]
Wherein, S<sub TranNum="107">ij</sub>for input picture respective pixel value, i wherein, the coordinate that j is each pixel, W<sub TranNum="108">ij</sub>?<be the contiguous function between neuron, T<sub TranNum="109">ij</sub>for dynamic threshold, Y<sub TranNum="110">ij</sub>for each neuronic output, f, g, h is scalar factor, and g<f<1 guarantees that dynamic threshold finally can be lower than neuronic state value with iteration, h is a very large scalar value, lifting threshold value that can be larger after assurance neuron firing, makes neuron not be excited in next iteration, and the intrinsic light-off period of intersecting visual cortical model neuron is T=log<sub TranNum="111">g</sub>(1+h/s<sub TranNum="112">ij</sub>), visible, the intersecting visual cortical model neuron firing cycle is relevant with the size of input stimulus.
Further, the Instrument image after intersecting visual cortical model is cut apart, comprises the following steps:
Step 1, setup parameter f=2, g=0.8, h=1000, initial threshold θ=125, send model by image and light a fire;
Η
f(x)=-x?log（x）-（1-x）log（1-x）
Further, calculate angle and utilize sobel gradient operator; Specific algorithm is:
The first step, regards template as gradient in some pixels, the center of this pixel corresponding templates, and specifically, the weighted value of the element on diagonal line is less than the element weighted value of horizontal direction and vertical direction, and X component is S
x, Y component is S
y, regard these components as gradient;
Second step, utilizes
be equivalent to each 2x2 area applications operator, then mean value of result of calculation in 3x3 region.
The object of the present invention is to provide a kind of cockpit instrument identification and pick-up unit automatically, described cockpit instrument automatically identifies and pick-up unit comprises: tested instrument, camera, image processing equipment, hard disk, display;
Described cockpit instrument automatically identification and pick-up unit employing S3C2440 as platform processor, camera described in described tested Instrument connection, described camera connects described image processing equipment, described image processing equipment connects described hard disk and display.
The automatic identification of cockpit instrument of the present invention and detection method and device have following excellent beneficial effect:
One, completely automatically identification and detect cockpit instrument of the present invention, need not manual intervention, can greatly alleviate human resources, the error of avoiding subjective factor to introduce;
Two, the present invention adopts simple processing links efficiently when design as far as possible; as adopt improved 0STU method to carry out binary conversion treatment, iterative morphological method extraction apparatus table skeleton, intersecting visual cortical model to image to extract edge and utilize sobel gradient operator to calculate angle etc., thereby the amount consuming time of whole recognition detection process is foreshortened in 40ms;
Three, instrument recognition detection focuses on how extracting edge and skeleton, determine the position of pointer, the present invention utilizes the edge that extracts pointer based on intersecting visual cortical model, on the basis that guarantees precision accuracy, improved the speed of operation, in addition, when calculating total indicator reading, adopt the maximum descent method of gradient and calculate angle in conjunction with priori, greatly saved the time of computing, in a word, the measuring accuracy of this programme can reach recognition detection requirement;
Four, the present invention has benefited from current image technique area research and reaches its maturity, much software provides powerful function library, as OpenCV etc., can between cross-platform, move, operating platforms such as Windows, Linux and Andriod, reduce so to a great extent the difficulty of software development, thereby development cost is lower.
Accompanying drawing explanation
Fig. 1 is the cockpit instrument that provides of the embodiment of the present invention process flow diagram of identification and detection method automatically;
Fig. 2 is the cockpit instrument that provides of the embodiment of the present invention structural representation of identification and pick-up unit automatically;
Fig. 3 is the template in the Stentiford thinning algorithm that provides of the embodiment of the present invention;
Fig. 4 is the ICM neuron Organization Chart that the embodiment of the present invention provides.
In figure: 1, tested instrument; 2, camera; 3, image processing equipment; 4, hard disk; 5, display.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with embodiment, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Fig. 1 shows cockpit instrument provided by the invention identification and detection method flow process automatically.For convenience of explanation, only show part related to the present invention.
Cockpit instrument of the present invention is identification and detection method automatically, and this cockpit instrument automatically identifies and detection method comprises the following steps:
Read in Instrument image;
Image is sampled;
Adopt non-linear Vector median filtering to carry out noise reduction process to image;
Adopt overall situation and partial situation's threshold method to combine, by Instrument image binaryzation, obtain binary image;
Image is carried out to refinement, accurately detect pointer, the pointer after thinning processing becomes single pixel wide pointer;
Utilize improved intersection vision mode, extract instrument edge;
According to priori, carry out learning training, find similar features, to the instrument comparison of classifying;
Utilize gradient method, calculate the angle of pointer;
By angle, and in conjunction with priori, evaluation, and store demonstration.
As a prioritization scheme of the embodiment of the present invention, image binaryzation adopts improved 0STU method to carry out binary conversion treatment to image.
As a prioritization scheme of the embodiment of the present invention, 0STU method is carried out binary conversion treatment idiographic flow to image and is:
The first step, reading images, and according to the concrete size of image ranks, by Image Automatic Segmentation, be the subimage of a series of variable r * r, conveniently image is carried out to the division of block;
Second step, in neighborhood, according to meter performance, is divided into target and background, adds up the intensity profile of each pixel, and what tonal range was comparatively approached is classified as a class, and calculates mathematical expectation and the variance of 2 category feature points, according to classical OTSU criterion, finds out local threshold T
1 (i);
The 3rd step, carries out binary conversion treatment to window, after carry out the operation of circulation process second step, until searching image is complete;
The 4th step, for avoiding that the point of edges of regions is produced to erroneous judgement, is considered as a pixel by each region, and gray-scale value is threshold value T
1 (i), view picture is solved to expectation, covariance, find out global threshold, erroneous judgement point is repaired.
As a prioritization scheme of the embodiment of the present invention, thinning processing adopts 3x3 template to extract the skeleton of cockpit instrument.
As a prioritization scheme of the embodiment of the present invention, the skeleton concrete grammar that 3x3 template is extracted cockpit instrument is:
Step 1, finds a pixel (i, j), makes pixel in image and the pixel matching in template A;
Step 6, repeating step (1) is to (5), otherwise, stop;
As a prioritization scheme of the embodiment of the present invention, extract edge and adopt intersecting visual cortical model to cut apart extraction to cockpit instrument.
As a prioritization scheme of the embodiment of the present invention, in intersecting visual cortical model, each neuron is for Last status F
ij[n-1] has memory function and state F
ijalong with its memory content of the variation of time can decay, the rate of decay is subject to the impact of decay factor f (f>1), and the mathematical expression of intersecting visual cortical model is as follows:
F
ij[n+1]=fF
ij[n]+S
ij+W
ij{Y}
T
ij[n+1]=g?T
ij[n]+h?Y
ij[n+1]
Wherein, S<sub TranNum="192">ij</sub>for input picture respective pixel value, i wherein, the coordinate that j is each pixel, W<sub TranNum="193">ij</sub>?<be the contiguous function between neuron, T<sub TranNum="194">ij</sub>for dynamic threshold, Y<sub TranNum="195">ij</sub>for each neuronic output, f, g, h is scalar factor, and g<f<1 guarantees that dynamic threshold finally can be lower than neuronic state value with iteration, h is a very large scalar value, lifting threshold value that can be larger after assurance neuron firing, makes neuron not be excited in next iteration, and the intrinsic light-off period of intersecting visual cortical model neuron is T=log<sub TranNum="196">g</sub>(1+h/s<sub TranNum="197">ij</sub>), visible, the intersecting visual cortical model neuron firing cycle is relevant with the size of input stimulus.
As a prioritization scheme of the embodiment of the present invention, the Instrument image after intersecting visual cortical model is cut apart, comprises the following steps:
Step 1, setup parameter f=2, g=0.8, h=1000, initial threshold θ=125, send model by image and light a fire;
Η
f(x)=-x?log（x）-（1-x）log（1-x）
As a prioritization scheme of the embodiment of the present invention, calculate angle and utilize sobel gradient operator; Specific algorithm is:
The first step, regards template as gradient in some pixels, the center of this pixel corresponding templates, and specifically, the weighted value of the element on diagonal line is less than the element weighted value of horizontal direction and vertical direction, and X component is S
x, Y component is S
y, regard these components as gradient;
Second step, utilizes
be equivalent to each 2x2 area applications operator, then mean value of result of calculation in 3x3 region.
Below in conjunction with drawings and the specific embodiments, application principle of the present invention is further described.
As shown in Figure 1, the automatic identification of the cockpit instrument of the embodiment of the present invention and detection method comprise the following steps:
S101: read in Instrument image;
S102: image is sampled;
S103: adopt non-linear Vector median filtering to carry out noise reduction process to image;
S104: adopt overall situation and partial situation's threshold method to combine, by Instrument image binaryzation, obtain binary image;
S105: image is carried out to refinement, accurately detect pointer, the pointer after thinning processing becomes single pixel wide pointer;
S106: utilize improved intersection vision mode (ICM), extract instrument edge;
S107: according to priori, carry out learning training, find similar features, to the instrument comparison of classifying;
S108; Utilize gradient method, calculate the angle of pointer;
S109: by angle, and in conjunction with priori, evaluation, and store demonstration.
As shown in Figure 2, the automatic identification of the cockpit instrument of the embodiment of the present invention and pick-up unit are mainly comprised of tested instrument 1, camera 2, image processing equipment 3, hard disk 4, display 5; According to actual needs and experience, the present invention adopts S3C2440 that Samsung produces as platform processor, utilizes 2 pairs of tested instrument 1 of CCD camera to carry out monitoring in real time and takes, and the processing by the image of typing by relevant design software is converted into its System Construction; When reality is tested, camera 2 is sent the instrument picture of shooting into image processing equipment 3, pre-service through related software, key point in Instrument image is cut apart, extract the profile of pointer, and its border is followed the tracks of, finally draw data, deposit data in hard disk 4 and show in display 5.
The present invention be take instrument on board as processing object, after reading images, whole process comprises sampling, noise reduction filtering, image binaryzation, refinement, extraction instrument edge, to image thinning (extraction skeleton), judgement pointer particular location with calculate these eight processing procedures of pointer angle, respectively each process is elaborated below
1, sampling
After device start, instrument image is reflected light and sends in prism, and be converted into electric signal (simulating signal) at device interior, via A/D converter, convert digital signal to, by signal storage in internal memory, by related software, carry out Treatment Analysis, for fear of due to angle, the gauge pointer deviation that the problems such as illumination cause, specific environment in conjunction with the present invention's application, select the frontlighting mode of source of parallel light, be that light is from front illuminated to instrument, video camera is placed in reflection of light direction, meeting under the prerequisite of nyquist sampling theorem, this video sequence is carried out to equal interval sampling, processing can reduce computation complexity like this, and it is simple to operate, being easy to software realizes,
2, noise reduction filtering
Instrument on board is converted to digital picture through camera will pass through optical reflection, sampling, all too many levels such as conversion, can introduce various noises and noise like this, thereby cause slightly deviation of the true precision of instrument and accuracy, in order to reach reduction noise, proofread and correct the distortion that illumination reflection causes, the present invention adopts spatial domain, the mode that frequency domain combines (being that homomorphic filtering combines with medium filtering) is carried out noise reduction process to Instrument image, homomorphic filtering is to process according to a kind of frequency domain of illumination-reflection model exploitation, by adjustment tonal range and contrast, strengthen image is carried out to noise reduction, by the method, be used for reducing the impact of illumination difference on image, medium filtering is a kind of non-linear filtering method of classics, its essence is exactly that the larger pixel of difference of conveying surrounding pixel gray-scale value changes to take the value approaching with surrounding pixel, thereby reach the elimination to isolated noise pixel, for the ease of retrieval and the quick noise of eliminating, the present invention adopts adaptive median filter (overall situation+local threshold is processed) to process,
3, image binaryzation
Image binaryzation is that the gray scale of the point on image is set to 0 or 255, make whole image present obvious black and white effect, it makes to need image to be processed to become simple, reduce details and reduced data volume, highlight area-of-interest simultaneously, separated identifying object and background, the key of the method is choosing of threshold value, after obtaining threshold value, greyscale image transitions is become to bianry image, the reach of threshold value, can be divided into global approach and local method, overall situation binaryzation refers to that entire image only has a threshold value, and local binarization refers to that entire image has a plurality of threshold values, threshold value is excessive or too smallly all can make target and background separation unclear, the pixel that all gray scales are less than or equal to threshold value is considered to target object, the pixel that is greater than threshold value is considered to background, visible, the precision of choosing the follow-up measurement of decision of threshold value, at present, domestic main employing Ostu method (OSTU), the method such as maximum entropy method (MEM) and minimum error method is carried out binary conversion treatment to image, but these class methods often computing time longer, for the little background of grey scale change and target extraction effect, not very desirable, for this reason, the present invention adopts improved 0STU method to carry out binary conversion treatment to image, idiographic flow is:
The first step, reading images, and according to the concrete size of image ranks, by Image Automatic Segmentation, be the subimage of a series of variable r * r, conveniently image is carried out to the division of block;
Second step, in neighborhood, according to meter performance, be divided into two classes (target and background), the intensity profile of adding up each pixel, what tonal range was comparatively approached is classified as a class, and calculate mathematical expectation and the variance of 2 category feature points, according to classical OTSU criterion, find out local threshold T
1 (i);
The 3rd step, carries out binary conversion treatment to this window, after carry out the operation of circulation process second step, until searching image is complete;
The 4th step, for avoiding that the point of edges of regions is produced to erroneous judgement, is considered as a pixel by each region, and gray-scale value is threshold value T
1 (i), view picture is solved to expectation, covariance, find out global threshold, erroneous judgement point is repaired;
This algorithm adopts top-down method, according to the size of image, image is cut apart to corresponding block template, using subgraph as the object of cutting apart, and consider the correlativity at block edge, utilize covariance to carry out the interpretation again of marginal point, the precision and the accuracy that have improved algorithm, utilize the method, and the present invention is when guaranteeing to extract target image, greatly improve the speed of algorithm process, obtained good binary conversion treatment effect;
4, thinning processing
Known according to measuring principle, the feature extraction of gauge pointer is a considerable link of this identification and detection method, image is after binary conversion treatment, the profile that only has indicator and table that dial plate image highlights, but how to give prominence to indicator, just become the very corn of a subject step, refinement is the process of formation object skeleton, so-called skeleton, with relatively less pixel, carry out exactly the shape of indicated object, the characteristic mainly representing with linear pointer for cockpit instrument, can the distinct pointer concrete position of pointing to of the extraction of skeleton, direction and length, and the extraction of jointing edge feature, for the reading of next step interpretation pointer indication is done necessary preparation, the method that tradition is extracted skeleton is Medial-Axis Transformation method, key step is: 1, calculate the distance between each object pixel and nearest edge pixel, 2, the Laplace operator of calculating range image, the pixel with higher value belongs to axis, and the present invention, on the basis of classic method, has introduced iterative morphological method, adopts 3x3 template to extract the skeleton of cockpit instrument, and concrete grammar is:
(1) find a pixel (i, j), make pixel in image and the pixel matching in template A;
(2), if center pixel is not an end points, making Betti number is 1, after pixel is labeled as to deletion;
(3) pixel of all matching template A is done to step (1) and (2);
(4) successively template B, C and D are repeated to (1) and (3);
(5), if there is pixel to be labeled deletion, is set to white and deleted;
(6) repeating step (1) is to (5), otherwise, stop;
As shown in Figure 3, the present invention is when scan image mates template, there is certain scanning sequency, the object of matching template A finds the pixel that can remove at the coboundary of destination object, therefore mate according to order from left to right, after according to order from top to bottom, mate, the pixel in B template matches target left side, according to bottom-up, order from left to right scans, the pixel of C template matches target feather edge, according to from right to left, bottom-up sequential scanning, D template matches right pixel, according to top-down, dextrosinistral sequential scanning, carry out interative computation step by step, finally calculate result,
5, extract edge
Edge is the border between destination object and background, if edge can be identified exactly in image, so all objects all can be positioned, and the base attribute of object (area, girth and shape) can be out measured, for the feature of cockpit instrument, to instrument particularly the extraction at pointer edge become key one step of analyzing total indicator reading, in general, be used for the 3 kinds of common operators that have at localizing objects edge
One, derivative operator, this place that is often used to the huge Strength Changes of sign generation;
Two, template matches, wherein edge carries out modeling by a very little image, shows as approximate perfect edge attributes;
Three, adopt some classical edge mathematical models, for example: Marr-Hildreth, Canny Edge edge detector etc.,
The priori that the method for traditional detection needs is few, but to shade, illumination variation is comparatively responsive, , thereby be guaranteed practical being difficult to of algorithm, the present invention is in conjunction with aviation actual needs, adopt intersecting visual cortical model (Intersecting Cortical Model) to cut apart extraction to cockpit instrument, when guaranteeing precision accuracy, greatly improved the speed of operation, ICM comes from the achievement in research of people to mammal visual cortex neuron impulsive synchronization oscillatory occurences, there is information transmission delay and Non-linear coupling modulating characteristic in biosystem, more approach biological vision neural network, being highly suitable for image processes, especially image is cut apart field,
ICM neuron is by dendron, non-linear connection modulation, pulse generating portion three parts form, the effect of dendron part is the input message receiving from adjacent neurons, it by linearity, connects input channel and feedback channel two parts form, the linear input channel that connects receives from the adjacent synapse input message in part, and feed back input passage is except receiving this local input message, also directly receive from outside stimulus information input, between neuron, by cynapse function, carry out the Kind of Nonlinear Dynamical System that interconnected formation is complicated, the generation of pulse depends on whether the input of dendron surpasses it and excite dynamic threshold, and this threshold value changes accordingly with the variation of neuron output state, as shown in Figure 4,
In ICM, each neuron is for Last status F
ij[n-1] has memory function and state F
ijalong with its memory content of the variation of time can decay, its rate of decay is subject to the impact of decay factor f (f>1), and the mathematical expression of ICM is as follows:
F
ij[n+1]=f?F
ij[n]+S
ij+W
ij{Y}
T
ij[n+1]=g?T
ij[n]+h?Y
ij[n+1]
Wherein, S<sub TranNum="276">ij</sub>for input picture respective pixel value, i wherein, the coordinate that j is each pixel, W<sub TranNum="277">ij</sub>?<be the contiguous function between neuron, T<sub TranNum="278">ij</sub>for dynamic threshold, Y<sub TranNum="279">ij</sub>for each neuronic output, f, g, h is scalar factor, and g<f<1 guarantees that dynamic threshold finally can be lower than neuronic state value with iteration, h is a very large scalar value, lifting threshold value that can be larger after assurance neuron firing, makes neuron not be excited in next iteration, and the intrinsic light-off period of ICM neuron is T=log<sub TranNum="280">g</sub>(1+h/s<sub TranNum="281">ij</sub>), visible, the ICM neuron firing cycle is relevant with the size of input stimulus;
When ICM processes for image, it is the locally-attached network of individual layer two dimension, neuron number is corresponding one by one with the number of pixel in image, first the neuron that in input picture, larger pixel value is corresponding lights a fire, output pulse, its threshold value uprush to after higher value in time with exponential damping, until F again
ij>T
ijtime neuron refire time, simultaneously, igniting neuron by contiguous function to neuron generation effect in its neighborhood, the neighborhood neuron that makes the to meet ignition condition igniting that is in succession hunted down, the image that the each iteration of ICM is exported is the region that has comprised input picture and marginal information in various degree all;
Visible, intersecting visual cortical model (ICM) possesses outstanding image segmentation ability, but ICM image segmentation not only depends on the choose reasonable of each parameter of ICM, also depend on optimal segmenting threshold, determining of loop iteration number of times, the neuronic loop iteration number of times of ICM need to be determined by man-machine interaction mode, this has destroyed advantage and the fast superiority of ICM processing speed that ICM does not need training process, therefore, select suitable criterion automatically to determine that the neuronic optimal segmenting threshold of ICM and loop iteration number of times are the keys that ICM image is cut apart, the present invention according to actual needs, concept in conjunction with fuzzy set and entropy, solve the threshold value of least confusion degree, effectively for the auto Segmentation of Instrument image, Instrument image after ICM is cut apart, its main method is briefly as follows:
Step 1, setup parameter f=2, g=0.8, h=1000, initial threshold θ=125, send model by image and light a fire;
Η
f(x)=-x?log（x）-（1-x）log（1-x）
6, template matches
Diversity for cockpit instrument, in order to identify fast and detect indicator reading, must be by priori, after learning training, find out the essential characteristic (range of certain class table, zero graduation position), complete the accurate judgement to indicator reading, the present invention adopts the method for interpretation instrument sign, instrument is sorted out to division, find out after instrument classification, can pass through priori, learn the range of instrument, the particular location of zero graduation and maximum scale, by gradient method, learn the angle information on minimum and maximum range, for finally calculating indicator angle and reading, carry out basis,
7, calculate angle
Extract pointer angle, it has been key one step that cockpit instrument is automatically identified and detected, research by the main flow algorithm to current is found, this type of algorithm exists and is not suitable for irregular instrument, the drawbacks such as computing time is tediously long, for this problem, the present invention utilizes sobel gradient operator to calculate angle, because treated image is binary image, gray-scale value only has 0 and 255, this is just angle of the pointer that extracts more easily condition of providing convenience, first, regard template as gradient in some pixels, the center of this pixel corresponding templates, specifically, the weighted value of the element on diagonal line is less than the element weighted value of horizontal direction and vertical direction, X component is S
x, Y component is S
y, regard these components as gradient, utilize
the method is equivalent to each the 2x2 area applications operator in 3x3 region, the mean value of result of calculation then, and specific practice is:
1,, for pointer, ask respectively the partial derivative of x, y direction;
2, the vector representation obtaining is intensity and the direction at pixel place;
3, by priori, learn the corresponding vector of zero graduation line;
4, difference solves angle.
Software emulation test
The present invention be take instrument as tested object, and partial test result, from test result, this software departs from the error of standard value in 0.3%, and measuring accuracy is high, in addition, the whole processing time of every width figure all in 40ms, the real-time demand of realistic identification and detection;
Table 1 test data
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (10)
1. cockpit instrument is identified and a detection method automatically, it is characterized in that, described cockpit instrument automatically identifies and detection method comprises the following steps:
Read in Instrument image;
Image is sampled;
Adopt non-linear Vector median filtering to carry out noise reduction process to image;
Adopt overall situation and partial situation's threshold method to combine, by Instrument image binaryzation, obtain binary image;
Image is carried out to refinement, accurately detect pointer, the pointer after thinning processing becomes single pixel wide pointer;
Utilize improved intersection vision mode, extract instrument edge;
According to priori, carry out learning training, find similar features, to the instrument comparison of classifying;
Utilize gradient method, calculate the angle of pointer;
By angle, and in conjunction with priori, evaluation, and store demonstration.
2. cockpit instrument as claimed in claim 1 is identified and detection method automatically, it is characterized in that, image binaryzation adopts improved 0STU method to carry out binary conversion treatment to image.
3. cockpit instrument as claimed in claim 2 is identified and detection method automatically, it is characterized in that, 0STU method is carried out binary conversion treatment idiographic flow to image and is:
The first step, reading images, and according to the concrete size of image ranks, by Image Automatic Segmentation, be the subimage of a series of variable r * r, conveniently image is carried out to the division of block;
Second step, in neighborhood, according to meter performance, is divided into target and background, adds up the intensity profile of each pixel, and what tonal range was comparatively approached is classified as a class, and calculates mathematical expectation and the variance of 2 category feature points, according to classical OTSU criterion, finds out local threshold T
1 (i);
The 3rd step, carries out binary conversion treatment to window, after carry out the operation of circulation process second step, until searching image is complete;
The 4th step, for avoiding that the point of edges of regions is produced to erroneous judgement, is considered as a pixel by each region, and gray-scale value is threshold value T
1 (i), view picture is solved to expectation, covariance, find out global threshold, erroneous judgement point is repaired.
4. cockpit instrument as claimed in claim 1 is identified and detection method automatically, it is characterized in that, thinning processing adopts 3x3 template to extract the skeleton of cockpit instrument.
5. cockpit instrument as claimed in claim 4 is identified and detection method automatically, it is characterized in that, the skeleton concrete grammar that 3x3 template is extracted cockpit instrument is:
Step 1, finds a pixel (i, j), makes pixel in image and the pixel matching in template A;
Step 2, if center pixel is not an end points, making Betti number is 1, after pixel is labeled as to deletion;
Step 3, does step (1) and (2) to the pixel of all matching template A;
Step 4, repeats (1) and (3) to template B, C and D successively;
Step 5, if there is pixel to be labeled deletion, pixel is set to white and deletes;
Step 6, repeating step (1) is to (5), otherwise, stop.
6. cockpit instrument as claimed in claim 1 is identified and detection method automatically, it is characterized in that, extracts edge and adopts intersecting visual cortical model to cut apart extraction to cockpit instrument.
7. cockpit instrument as claimed in claim 6 is identified and detection method automatically, it is characterized in that, in intersecting visual cortical model, each neuron is for Last status F
ij[n-1] has memory function and state F
ijalong with its memory content of the variation of time can decay, the rate of decay is subject to the impact of decay factor f (f>1), and the mathematical expression of intersecting visual cortical model is as follows:
F
ij[n+1]=fF
ij[n]+S
ij+W
ij{Y}
T
ij[n+1]=g?T
ij[n]+hY
ij[n+1]
Wherein, S<sub TranNum="369">ij</sub>for input picture respective pixel value, i wherein, the coordinate that j is each pixel, W<sub TranNum="370">ij</sub>?<be the contiguous function between neuron, T<sub TranNum="371">ij</sub>for dynamic threshold, Y<sub TranNum="372">ij</sub>for each neuronic output, f, g, h is scalar factor, and g<f<1 guarantees that dynamic threshold finally can be lower than neuronic state value with iteration, h is a very large scalar value, lifting threshold value that can be larger after assurance neuron firing, makes neuron not be excited in next iteration, and the intrinsic light-off period of intersecting visual cortical model neuron is T=log<sub TranNum="373">g</sub>(1+h/s<sub TranNum="374">ij</sub>), visible, the intersecting visual cortical model neuron firing cycle is relevant with the size of input stimulus.
8. cockpit instrument as claimed in claim 6 is identified and detection method automatically, it is characterized in that, the Instrument image after intersecting visual cortical model is cut apart, comprises the following steps:
Step 1, setup parameter f=2, g=0.8, h=1000, initial threshold θ=125, send model by image and light a fire;
Step 2, complete after initial segmentation, determine membership function, making the expectation of background gray scale is μ
0, the gray scale expectation of target is μ
1, C is the difference of maximum gradation value and minimum gradation value, between the gray-scale value of pixel X and the mathematical expectation of this class pixel, difference is less arbitrarily, so member function μ
Χ(x) value is just larger, given threshold value T, and member function is defined as follows;
Step 3, according to shannon function H
f(x), to all gray-scale value g summations, wherein line number and the columns of N and M presentation video, h is grey level histogram, calculates the entropy E (t) of fuzzy set, if E (t) does not meet the condition that sets, change threshold value, repeating step (1) and (2), when E (t) is minimum value, t is the threshold value that minimizes blur level;
Η
f(x)=-x?log（x）-（1-x）log（1-x）
Step 4, by reaching the image minimizing after Threshold segmentation, carry out binary conversion treatment so that with skeleton image matching, find out pointer position.
9. cockpit instrument as claimed in claim 1 is identified and detection method automatically, it is characterized in that, calculates angle and utilizes sobel gradient operator; Specific algorithm is:
The first step, regards template as gradient in some pixels, the center of this pixel corresponding templates, and specifically, the weighted value of the element on diagonal line is less than the element weighted value of horizontal direction and vertical direction, and X component is S
x, Y component is S
y, regard these components as gradient;
Second step, utilizes
be equivalent to each 2x2 area applications operator, then mean value of result of calculation in 3x3 region.
10. cockpit instrument is identified and a pick-up unit automatically, it is characterized in that, described cockpit instrument automatically identifies and pick-up unit comprises: tested instrument, camera, image processing equipment, hard disk, display;
Described cockpit instrument automatically identification and pick-up unit employing S3C2440 as platform processor, camera described in described tested Instrument connection, described camera connects described image processing equipment, described image processing equipment connects described hard disk and display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310455647.9A CN103528617B (en) | 2013-09-27 | 2013-09-27 | A kind of cockpit instrument identifies and detection method and device automatically |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310455647.9A CN103528617B (en) | 2013-09-27 | 2013-09-27 | A kind of cockpit instrument identifies and detection method and device automatically |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103528617A true CN103528617A (en) | 2014-01-22 |
| CN103528617B CN103528617B (en) | 2016-08-10 |
Family
ID=49930813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310455647.9A Expired - Fee Related CN103528617B (en) | 2013-09-27 | 2013-09-27 | A kind of cockpit instrument identifies and detection method and device automatically |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103528617B (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103776482A (en) * | 2014-02-20 | 2014-05-07 | 湖南大学 | Image detection method for scales of non-ruler-line pointer instrument |
| CN103994786A (en) * | 2014-06-04 | 2014-08-20 | 湖南大学 | Image detecting method for arc ruler lines of pointer instrument scale |
| CN105354575A (en) * | 2015-10-21 | 2016-02-24 | 江苏科技大学 | Image binarization threshold determination method in sea-sky-line detection |
| CN105740829A (en) * | 2016-02-02 | 2016-07-06 | 暨南大学 | Scanning line processing based automatic reading method for pointer instrument |
| CN105727457A (en) * | 2014-12-11 | 2016-07-06 | 苏州雷泰医疗科技有限公司 | Radiation treatment parameter verification apparatus and method, and radiation treatment device |
| CN106650697A (en) * | 2016-12-30 | 2017-05-10 | 亿嘉和科技股份有限公司 | Instrument scale recognition method |
| CN106920398A (en) * | 2017-04-27 | 2017-07-04 | 深圳大图科创技术开发有限公司 | A kind of intelligent vehicle license plate recognition system |
| CN107123116A (en) * | 2017-04-25 | 2017-09-01 | 航天科技控股集团股份有限公司 | Based on cloud platform Full-automatic instrument detecting system and detection method |
| CN107153848A (en) * | 2017-06-15 | 2017-09-12 | 南京工程学院 | Instrument image automatic identifying method based on OpenCV |
| CN107231521A (en) * | 2017-04-29 | 2017-10-03 | 安徽慧视金瞳科技有限公司 | Camera automatic positioning method is used in a kind of meter reading identification |
| CN107347060A (en) * | 2017-06-14 | 2017-11-14 | 武汉万千无限科技有限公司 | A kind of intelligent business information based on wireless terminal provides control system |
| CN107657601A (en) * | 2017-07-28 | 2018-02-02 | 国网山东省电力公司济南供电公司 | A kind of substation equipment division physical location monitoring device and method |
| CN108337323A (en) * | 2018-03-19 | 2018-07-27 | 深圳增强现实技术有限公司 | A kind of metering instrument data AR Compare Systems and method based on full terminal |
| CN108564085A (en) * | 2018-03-13 | 2018-09-21 | 南京大学 | A kind of method of automatic reading pointer type instrument reading |
| CN109910610A (en) * | 2019-02-18 | 2019-06-21 | 武汉格瑞恩电子仪表有限公司 | Combination instrument |
| CN109948469A (en) * | 2019-03-01 | 2019-06-28 | 吉林大学 | The automatic detection recognition method of crusing robot instrument based on deep learning |
| CN110308346A (en) * | 2019-06-24 | 2019-10-08 | 中国航空无线电电子研究所 | Cockpit display system automatic test approach and system based on image recognition |
| CN110796139A (en) * | 2019-10-17 | 2020-02-14 | 中国测试技术研究院辐射研究所 | Method for positioning and dividing indication value pattern in test/detection/calibration/verification |
| CN111598913A (en) * | 2020-04-28 | 2020-08-28 | 福建省海峡智汇科技有限公司 | Image segmentation method and system based on robot vision |
| CN111639715A (en) * | 2020-06-01 | 2020-09-08 | 重庆大学 | Automobile instrument assembly quality prediction method and system based on LS-SVM |
| CN112419278A (en) * | 2020-11-25 | 2021-02-26 | 上海应用技术大学 | Deep learning-based solid wood floor classification method |
| CN112508084A (en) * | 2020-12-04 | 2021-03-16 | 宁波智能装备研究院有限公司 | Machine vision detection method based on fuzzy similarity measurement in complex industrial environment |
| CN113312941A (en) * | 2020-02-26 | 2021-08-27 | 北京同邦卓益科技有限公司 | Method and device for monitoring instrument panel |
| CN114140678A (en) * | 2021-11-23 | 2022-03-04 | 北京东方国信科技股份有限公司 | Scale recognition method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1468396A1 (en) * | 2002-01-23 | 2004-10-20 | Honeywell International Inc. | Method, data structure, and system for image feature extraction |
| US20090190795A1 (en) * | 2008-01-30 | 2009-07-30 | Moses Derkalousdian | Gauge monitoring methods, devices and systems |
| CN101577003A (en) * | 2009-06-05 | 2009-11-11 | 北京航空航天大学 | Image segmenting method based on improvement of intersecting visual cortical model |
| CN101620682A (en) * | 2008-06-30 | 2010-01-06 | 汉王科技股份有限公司 | Method and system for automatically identifying readings of pointer type meters |
| US20120106788A1 (en) * | 2010-10-29 | 2012-05-03 | Keyence Corporation | Image Measuring Device, Image Measuring Method, And Computer Program |
| CN102521560A (en) * | 2011-11-14 | 2012-06-27 | 上海交通大学 | Instrument pointer image identification method of high-robustness rod |
| CN102799867A (en) * | 2012-07-09 | 2012-11-28 | 哈尔滨工业大学 | Meter pointer angle identification method based on image processing |
| US20130070099A1 (en) * | 2011-09-20 | 2013-03-21 | Honeywell International Inc. | Image based dial gauge reading |
-
2013
- 2013-09-27 CN CN201310455647.9A patent/CN103528617B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1468396A1 (en) * | 2002-01-23 | 2004-10-20 | Honeywell International Inc. | Method, data structure, and system for image feature extraction |
| US20090190795A1 (en) * | 2008-01-30 | 2009-07-30 | Moses Derkalousdian | Gauge monitoring methods, devices and systems |
| CN101620682A (en) * | 2008-06-30 | 2010-01-06 | 汉王科技股份有限公司 | Method and system for automatically identifying readings of pointer type meters |
| CN101577003A (en) * | 2009-06-05 | 2009-11-11 | 北京航空航天大学 | Image segmenting method based on improvement of intersecting visual cortical model |
| US20120106788A1 (en) * | 2010-10-29 | 2012-05-03 | Keyence Corporation | Image Measuring Device, Image Measuring Method, And Computer Program |
| US20130070099A1 (en) * | 2011-09-20 | 2013-03-21 | Honeywell International Inc. | Image based dial gauge reading |
| CN102521560A (en) * | 2011-11-14 | 2012-06-27 | 上海交通大学 | Instrument pointer image identification method of high-robustness rod |
| CN102799867A (en) * | 2012-07-09 | 2012-11-28 | 哈尔滨工业大学 | Meter pointer angle identification method based on image processing |
Non-Patent Citations (2)
| Title |
|---|
| 吴浪: "船舶机舱仪表监测系统研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 吴海滨等: "基于OTSU的动态结合全局阈值的图象分割", 《大气与环境光学学报》 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103776482B (en) * | 2014-02-20 | 2016-09-07 | 湖南大学 | The image detecting method of the scale of pointer instrument without scale line |
| CN103776482A (en) * | 2014-02-20 | 2014-05-07 | 湖南大学 | Image detection method for scales of non-ruler-line pointer instrument |
| CN103994786A (en) * | 2014-06-04 | 2014-08-20 | 湖南大学 | Image detecting method for arc ruler lines of pointer instrument scale |
| CN105727457A (en) * | 2014-12-11 | 2016-07-06 | 苏州雷泰医疗科技有限公司 | Radiation treatment parameter verification apparatus and method, and radiation treatment device |
| CN105727457B (en) * | 2014-12-11 | 2019-07-23 | 苏州雷泰医疗科技有限公司 | A kind of radiation treatment parameters verifying device and radiotherapy equipment and verification method |
| CN105354575B (en) * | 2015-10-21 | 2018-05-22 | 江苏科技大学 | Image binaryzation threshold value determines method in a kind of sea horizon detection |
| CN105354575A (en) * | 2015-10-21 | 2016-02-24 | 江苏科技大学 | Image binarization threshold determination method in sea-sky-line detection |
| CN105740829A (en) * | 2016-02-02 | 2016-07-06 | 暨南大学 | Scanning line processing based automatic reading method for pointer instrument |
| CN106650697A (en) * | 2016-12-30 | 2017-05-10 | 亿嘉和科技股份有限公司 | Instrument scale recognition method |
| CN106650697B (en) * | 2016-12-30 | 2019-11-15 | 亿嘉和科技股份有限公司 | A kind of meter dial recognition methods |
| CN107123116A (en) * | 2017-04-25 | 2017-09-01 | 航天科技控股集团股份有限公司 | Based on cloud platform Full-automatic instrument detecting system and detection method |
| CN106920398A (en) * | 2017-04-27 | 2017-07-04 | 深圳大图科创技术开发有限公司 | A kind of intelligent vehicle license plate recognition system |
| CN107231521A (en) * | 2017-04-29 | 2017-10-03 | 安徽慧视金瞳科技有限公司 | Camera automatic positioning method is used in a kind of meter reading identification |
| CN107347060A (en) * | 2017-06-14 | 2017-11-14 | 武汉万千无限科技有限公司 | A kind of intelligent business information based on wireless terminal provides control system |
| CN107153848A (en) * | 2017-06-15 | 2017-09-12 | 南京工程学院 | Instrument image automatic identifying method based on OpenCV |
| CN107657601A (en) * | 2017-07-28 | 2018-02-02 | 国网山东省电力公司济南供电公司 | A kind of substation equipment division physical location monitoring device and method |
| CN108564085A (en) * | 2018-03-13 | 2018-09-21 | 南京大学 | A kind of method of automatic reading pointer type instrument reading |
| CN108564085B (en) * | 2018-03-13 | 2020-07-14 | 南京大学 | Method for automatically reading of pointer type instrument |
| CN108337323A (en) * | 2018-03-19 | 2018-07-27 | 深圳增强现实技术有限公司 | A kind of metering instrument data AR Compare Systems and method based on full terminal |
| CN109910610A (en) * | 2019-02-18 | 2019-06-21 | 武汉格瑞恩电子仪表有限公司 | Combination instrument |
| CN109948469A (en) * | 2019-03-01 | 2019-06-28 | 吉林大学 | The automatic detection recognition method of crusing robot instrument based on deep learning |
| CN110308346A (en) * | 2019-06-24 | 2019-10-08 | 中国航空无线电电子研究所 | Cockpit display system automatic test approach and system based on image recognition |
| CN110308346B (en) * | 2019-06-24 | 2021-10-26 | 中国航空无线电电子研究所 | Automatic testing method and system for cockpit display system based on image recognition |
| CN110796139A (en) * | 2019-10-17 | 2020-02-14 | 中国测试技术研究院辐射研究所 | Method for positioning and dividing indication value pattern in test/detection/calibration/verification |
| CN110796139B (en) * | 2019-10-17 | 2023-06-23 | 中国测试技术研究院辐射研究所 | Method for positioning and dividing pattern of indication value in test/detection/calibration/verification |
| CN113312941A (en) * | 2020-02-26 | 2021-08-27 | 北京同邦卓益科技有限公司 | Method and device for monitoring instrument panel |
| CN111598913A (en) * | 2020-04-28 | 2020-08-28 | 福建省海峡智汇科技有限公司 | Image segmentation method and system based on robot vision |
| CN111598913B (en) * | 2020-04-28 | 2023-03-17 | 福建省海峡智汇科技有限公司 | Image segmentation method and system based on robot vision |
| CN111639715B (en) * | 2020-06-01 | 2023-06-06 | 重庆大学 | LS-SVM-based automobile instrument assembly quality prediction method and system |
| CN111639715A (en) * | 2020-06-01 | 2020-09-08 | 重庆大学 | Automobile instrument assembly quality prediction method and system based on LS-SVM |
| CN112419278A (en) * | 2020-11-25 | 2021-02-26 | 上海应用技术大学 | Deep learning-based solid wood floor classification method |
| CN112419278B (en) * | 2020-11-25 | 2024-04-19 | 上海应用技术大学 | Solid wood floor classification method based on deep learning |
| CN112508084A (en) * | 2020-12-04 | 2021-03-16 | 宁波智能装备研究院有限公司 | Machine vision detection method based on fuzzy similarity measurement in complex industrial environment |
| CN112508084B (en) * | 2020-12-04 | 2022-05-03 | 宁波智能装备研究院有限公司 | Machine vision detection method based on fuzzy similarity measurement in complex industrial environment |
| CN114140678A (en) * | 2021-11-23 | 2022-03-04 | 北京东方国信科技股份有限公司 | Scale recognition method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103528617B (en) | 2016-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103528617A (en) | Cockpit instrument automatic recognizing and detecting method and device | |
| CN109190473A (en) | The application of a kind of " machine vision understanding " in remote monitoriong of electric power | |
| CN108830332A (en) | A kind of vision vehicle checking method and system | |
| CN105574550A (en) | Vehicle identification method and device | |
| CN109886928A (en) | A kind of target cell labeling method, device, storage medium and terminal device | |
| CN109977191A (en) | Problem map detection method, device, electronic equipment and medium | |
| CN108764134A (en) | A kind of automatic positioning of polymorphic type instrument and recognition methods suitable for crusing robot | |
| CN106778703A (en) | The method and apparatus of electric marking | |
| CN111242899B (en) | Image-based flaw detection method and computer-readable storage medium | |
| CN111724355A (en) | Image measuring method for abalone body type parameters | |
| CN104680185B (en) | Hyperspectral image classification method based on boundary point reclassification | |
| CN100470578C (en) | Science instrument working state monitoring method based on computer vision | |
| CN116245230B (en) | Operation inspection and trend analysis method and system for power station equipment | |
| CN113222913A (en) | Circuit board defect detection positioning method and device and storage medium | |
| CN114550017B (en) | Pine wilt disease integrated early warning and detecting method and device based on mobile terminal | |
| CN111553184A (en) | Small target detection method and device based on electronic purse net and electronic equipment | |
| CN110321867A (en) | Shelter target detection method based on part constraint network | |
| CN110335242A (en) | A kind of tire X-ray defect detection method based on multi-model fusion | |
| CN112966921A (en) | Innovation ability evaluation method based on programming ability evaluation | |
| CN107657262A (en) | A kind of computer automatic sorting Accuracy Assessment | |
| CN114037993A (en) | Substation pointer instrument reading method and device, storage medium and electronic equipment | |
| CN108985308A (en) | The system and method for electric energy meter presentation quality is quickly analyzed based on data mining algorithm | |
| CN113538411A (en) | Insulator defect detection method and device | |
| CN113065556A (en) | Digital instrument positioning and digital identification method and device and computer equipment | |
| CN112184708B (en) | Sperm survival rate detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160810 Termination date: 20170927 |